Predicting membrane protein types by incorporating protein topology, domains, signal peptides, and physicochemical properties into the general form of Chou’s pseudo amino acid composition

iHSP-PseRAAAC: Identifying the heat shock protein families using pseudo reduced amino acid alphabet composition

“…[79] and demonstrated by Eqs. (28) to (32) of Ref. [12], and hence has been widely recognized and increasingly adopted by investigators to examine the quality of various predictors (see, e.g., Refs.…”

“…To completely avoid losing the sequence order information, the pseudo amino acid composition (PseAAC) was proposed [21,22] to replace the simple AAC model for representing the sample of a protein. Ever since the concept of PseAAC was proposed in 2001 [21], it has penetrated into nearly all of the areas of protein attribute prediction such as identifying bacterial virulent proteins [23], predicting supersecondary structure [24], predicting protein subcellular location [25][26][27], predicting membrane protein types [28], discriminating outer membrane proteins [29], identifying antibacterial peptides [30], identifying allergenic proteins [31], predicting metalloproteinase family [32], predicting protein structural class [33], identifying G-protein-coupled receptors (GPCRs) and their types [34], identifying protein quaternary structural attributes [35], predicting protein submitochondria locations [36], identifying risk type of human papillomaviruses [37], identifying cyclin proteins [38], predicting GABA A receptor proteins [39], predicting subchloroplast locations [40], and classifying amino acids [41], among many others (see a long list of articles cited in the References section of Ref. [12]).…”

“…One of the most simple PseAAC modes is the so-called n-peptide composition: when n = 1, it is reduced to AAC; when n = 2, it is reduced to dipeptide composition [28,30,[50][51][52]; when n = 3, it is reduced to tripeptide composition [53]; and so forth. Although the n-peptide composition can incorporate some sort of sequence order information when n P 2, the dimension of PseAAC formed in this way will increase rapidly.…”

A GASVM Algorithm for Predicting Protein Structure Classes

“…Experiments show that for low similarity datasets this method also has a high prediction accuracy. After extracting effective features, you can use a variety of classification algorithms to classify the extracted feature vector, such as Neural networks [7], Support vector machines [8], Bayesian classification [9], rough set theory [10], Fuzzy classification [11], Logit Boost classifier [12], Information about the differences method [13], etc. Thus, an appropriate machine learning algorithm is very important to the prediction.…”

A Short Survey on Genetic Sequences, Chou’s Pseudo Amino Acid Composition and its Combination with Fuzzy Set Theory

“…This approach has been employed in a large number of studies of protein attributes, such as identifying bacterial virulent proteins [2], predicting super-secondary structure [3], predicting protein subcellular location [4][5][6], predicting membrane protein types [7], discriminating outer membrane proteins [8], identifying antibacterial peptides [9,10], identifying allergenic proteins [11], predicting metalloproteinase family [12], predicting protein structural class [13], identifying GPCRs and their types [14], identifying protein quaternary structural attributes [15], predicting protein submitochondria locations [16], identifying risk type of human papillomaviruses [17], identifying cyclin proteins [18], predicting GABA(A) receptor proteins [19], among many others (see a long list of papers cited in the References section of [20]). Recently, the concept of PseAAC was further extended to represent the feature vectors of DNA and nucleotides [21,22], as well as other biological samples (see, for example [23][24][25]).…”